1 files changed, 99 insertions, 21 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d3f6e3e42a11..04f39ea15898 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1091,6 +1091,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
 };
 #endif /* CONFIG_XFS_RT */
 
+#ifdef DEBUG
+static void
+xfs_check_atomic_cow_conversion(
+	struct xfs_inode		*ip,
+	xfs_fileoff_t			offset_fsb,
+	xfs_filblks_t			count_fsb,
+	const struct xfs_bmbt_irec	*cmap)
+{
+	struct xfs_iext_cursor		icur;
+	struct xfs_bmbt_irec		cmap2 = { };
+
+	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2))
+		xfs_trim_extent(&cmap2, offset_fsb, count_fsb);
+
+	ASSERT(cmap2.br_startoff == cmap->br_startoff);
+	ASSERT(cmap2.br_blockcount == cmap->br_blockcount);
+	ASSERT(cmap2.br_startblock == cmap->br_startblock);
+	ASSERT(cmap2.br_state == cmap->br_state);
+}
+#else
+# define xfs_check_atomic_cow_conversion(...)	((void)0)
+#endif
+
 static int
 xfs_atomic_write_cow_iomap_begin(
 	struct inode		*inode,
@@ -1102,9 +1125,10 @@ xfs_atomic_write_cow_iomap_begin(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	const xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
-	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
+	const xfs_fileoff_t	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	const xfs_fileoff_t	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+	const xfs_filblks_t	count_fsb = end_fsb - offset_fsb;
+	xfs_filblks_t		hole_count_fsb;
 	int			nmaps = 1;
 	xfs_filblks_t		resaligned;
 	struct xfs_bmbt_irec	cmap;
@@ -1130,7 +1154,7 @@ xfs_atomic_write_cow_iomap_begin(
 		return -EAGAIN;
 
 	trace_xfs_iomap_atomic_write_cow(ip, offset, length);
-
+retry:
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 	if (!ip->i_cowfp) {
@@ -1141,14 +1165,22 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+
+		/*
+		 * cmap could extend outside the write range due to previous
+		 * speculative preallocations.  We must trim cmap to the write
+		 * range because the cow fork treats written mappings to mean
+		 * "write in progress".
+		 */
 		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
-	end_fsb = cmap.br_startoff;
-	count_fsb = end_fsb - offset_fsb;
+	hole_count_fsb = cmap.br_startoff - offset_fsb;
 
-	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
+	resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb,
 			xfs_get_cowextsz_hint(ip));
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
@@ -1169,8 +1201,10 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
-		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		xfs_trans_cancel(tp);
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
@@ -1182,7 +1216,7 @@ xfs_atomic_write_cow_iomap_begin(
 	 * atomic writes to that same range will be aligned (and don't require
 	 * this COW-based method).
 	 */
-	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+	error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC |
 			XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps);
 	if (error) {
@@ -1195,21 +1229,43 @@ xfs_atomic_write_cow_iomap_begin(
 	if (error)
 		goto out_unlock;
 
+	/*
+	 * cmap could map more blocks than the range we passed into bmapi_write
+	 * because of EXTSZALIGN or adjacent pre-existing unwritten mappings
+	 * that were merged.  Trim cmap to the original write range so that we
+	 * don't convert more than we were asked to do for this write.
+	 */
+	xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+
 found:
 	if (cmap.br_state != XFS_EXT_NORM) {
-		error = xfs_reflink_convert_cow_locked(ip, offset_fsb,
-				count_fsb);
+		error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff,
+				cmap.br_blockcount);
 		if (error)
 			goto out_unlock;
 		cmap.br_state = XFS_EXT_NORM;
+		xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb,
+				&cmap);
 	}
 
-	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
-	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
+	trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap);
 	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);
 
+convert_delay:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap,
+			NULL);
+	if (error)
+		return error;
+
+	/*
+	 * Try the lookup again, because the delalloc conversion might have
+	 * turned the COW mapping into unwritten, but we need it to be in
+	 * written state.
+	 */
+	goto retry;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -1702,6 +1758,8 @@ xfs_buffered_write_iomap_begin(
 	struct iomap		*iomap,
 	struct iomap		*srcmap)
 {
+	struct iomap_iter	*iter = container_of(iomap, struct iomap_iter,
+						     iomap);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
@@ -1767,21 +1825,41 @@ xfs_buffered_write_iomap_begin(
 	}
 
 	/*
-	 * For zeroing, trim a delalloc extent that extends beyond the EOF
-	 * block.  If it starts beyond the EOF block, convert it to an
+	 * For zeroing, trim extents that extend beyond the EOF block. If a
+	 * delalloc extent starts beyond the EOF block, convert it to an
 	 * unwritten extent.
 	 */
-	if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb &&
-	    isnullstartblock(imap.br_startblock)) {
+	if (flags & IOMAP_ZERO) {
 		xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
+		u64 end;
 
-		if (offset_fsb >= eof_fsb)
+		if (isnullstartblock(imap.br_startblock) &&
+		    offset_fsb >= eof_fsb)
 			goto convert_delay;
-		if (end_fsb > eof_fsb) {
+		if (offset_fsb < eof_fsb && end_fsb > eof_fsb)
 			end_fsb = eof_fsb;
-			xfs_trim_extent(&imap, offset_fsb,
-					end_fsb - offset_fsb);
+
+		/*
+		 * Look up dirty folios for unwritten mappings within EOF.
+		 * Providing this bypasses the flush iomap uses to trigger
+		 * extent conversion when unwritten mappings have dirty
+		 * pagecache in need of zeroing.
+		 *
+		 * Trim the mapping to the end pos of the lookup, which in turn
+		 * was trimmed to the end of the batch if it became full before
+		 * the end of the mapping.
+		 */
+		if (imap.br_state == XFS_EXT_UNWRITTEN &&
+		    offset_fsb < eof_fsb) {
+			loff_t len = min(count,
+					 XFS_FSB_TO_B(mp, imap.br_blockcount));
+
+			end = iomap_fill_dirty_folios(iter, offset, len);
+			end_fsb = min_t(xfs_fileoff_t, end_fsb,
+					XFS_B_TO_FSB(mp, end));
 		}
+
+		xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
 	}
 
 	/*